- Linux-kselftest-mirror - lists.linaro.org

[PATCH] selftests/harness: remove use of LINE_MAX

by Edward Liaw

Android was seeing a compliation error because its C library does not define LINE_MAX. This replaces the use of LINE_MAX / snprintf with asprintf, which will change the behavior to not truncate the test name if it is over 2048 chars long. See also: https://github.com/llvm/llvm-project/issues/88119 Signed-off-by: Edward Liaw <edliaw(a)google.com> --- tools/testing/selftests/kselftest_harness.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 4fd735e48ee7..70fedd2411ed 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -1156,7 +1156,7 @@ void __run_test(struct __fixture_metadata *f, struct __test_metadata *t) { struct __test_xfail *xfail; - char test_name[LINE_MAX]; + char *test_name; const char *diagnostic; /* reset test struct */ @@ -1164,8 +1164,8 @@ void __run_test(struct __fixture_metadata *f, t->trigger = 0; memset(t->results->reason, 0, sizeof(t->results->reason)); - snprintf(test_name, sizeof(test_name), "%s%s%s.%s", - f->name, variant->name[0] ? "." : "", variant->name, t->name); + asprintf(&test_name, "%s%s%s.%s", f->name, + variant->name[0] ? "." : "", variant->name, t->name); ksft_print_msg(" RUN %s ...\n", test_name); @@ -1203,6 +1203,7 @@ void __run_test(struct __fixture_metadata *f, ksft_test_result_code(t->exit_code, test_name, diagnostic ? "%s" : "", diagnostic); + free(test_name); } static int test_harness_run(int argc, char **argv) -- 2.44.0.683.g7961c838ac-goog

1 year, 7 months

2
3
0 0

[PATCH] selftests/rseq: take large C-state exit latency into consideration

by Zide Chen

Currently, the migration worker delays 1-10 us, assuming that one KVM_RUN iteration only takes a few microseconds. But if C-state exit latencies are large enough, for example, hundreds or even thousands of microseconds on server CPUs, it may happen that it's not able to bring the target CPU out of C-state before the migration worker starts to migrate it to the next CPU. If the system workload is light, most CPUs could be at a certain level of C-state, and the vCPU thread may waste milliseconds before it can actually migrate to a new CPU. Thus, the tests may be inefficient in such systems, and in some cases it may fail the migration/KVM_RUN ratio sanity check. Since we are not able to turn off the cpuidle sub-system in run time, this patch creates an idle thread on every CPU to prevent them from entering C-states. Additionally, seems it's reasonable to randomize the length of usleep(), other than delay in a fixed pattern. Signed-off-by: Zide Chen <zide.chen(a)intel.com> --- tools/testing/selftests/kvm/rseq_test.c | 76 ++++++++++++++++++++++--- 1 file changed, 69 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index 28f97fb52044..d6e8b851d29e 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -11,6 +11,7 @@ #include <syscall.h> #include <sys/ioctl.h> #include <sys/sysinfo.h> +#include <sys/resource.h> #include <asm/barrier.h> #include <linux/atomic.h> #include <linux/rseq.h> @@ -29,9 +30,10 @@ #define NR_TASK_MIGRATIONS 100000 static pthread_t migration_thread; +static pthread_t *idle_threads; static cpu_set_t possible_mask; -static int min_cpu, max_cpu; -static bool done; +static int min_cpu, max_cpu, nproc; +static volatile bool done; static atomic_t seq_cnt; @@ -150,7 +152,7 @@ static void *migration_worker(void *__rseq_tid) * Use usleep() for simplicity and to avoid unnecessary kernel * dependencies. */ - usleep((i % 10) + 1); + usleep((rand() % 10) + 1); } done = true; return NULL; @@ -158,7 +160,7 @@ static void *migration_worker(void *__rseq_tid) static void calc_min_max_cpu(void) { - int i, cnt, nproc; + int i, cnt; TEST_REQUIRE(CPU_COUNT(&possible_mask) >= 2); @@ -186,6 +188,61 @@ static void calc_min_max_cpu(void) "Only one usable CPU, task migration not possible"); } +static void *idle_thread_fn(void *__idle_cpu) +{ + int r, cpu = (int)(unsigned long)__idle_cpu; + cpu_set_t allowed_mask; + + CPU_ZERO(&allowed_mask); + CPU_SET(cpu, &allowed_mask); + + r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask); + TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)", + errno, strerror(errno)); + + /* lowest priority, trying to prevent it from entering C-states */ + r = setpriority(PRIO_PROCESS, 0, 19); + TEST_ASSERT(!r, "setpriority failed, errno = %d (%s)", + errno, strerror(errno)); + + while(!done); + + return NULL; +} + +static void spawn_threads(void) +{ + int cpu; + + /* Run a dummy thread on every CPU */ + for (cpu = min_cpu; cpu <= max_cpu; cpu++) { + if (!CPU_ISSET(cpu, &possible_mask)) + continue; + + pthread_create(&idle_threads[cpu], NULL, idle_thread_fn, + (void *)(unsigned long)cpu); + } + + pthread_create(&migration_thread, NULL, migration_worker, + (void *)(unsigned long)syscall(SYS_gettid)); +} + +static void join_threads(void) +{ + int cpu; + + pthread_join(migration_thread, NULL); + + for (cpu = min_cpu; cpu <= max_cpu; cpu++) { + if (!CPU_ISSET(cpu, &possible_mask)) + continue; + + pthread_join(idle_threads[cpu], NULL); + } + + free(idle_threads); +} + int main(int argc, char *argv[]) { int r, i, snapshot; @@ -199,6 +256,12 @@ int main(int argc, char *argv[]) calc_min_max_cpu(); + srand(time(NULL)); + + idle_threads = malloc(sizeof(pthread_t) * nproc); + TEST_ASSERT(idle_threads, "malloc failed, errno = %d (%s)", errno, + strerror(errno)); + r = rseq_register_current_thread(); TEST_ASSERT(!r, "rseq_register_current_thread failed, errno = %d (%s)", errno, strerror(errno)); @@ -210,8 +273,7 @@ int main(int argc, char *argv[]) */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - pthread_create(&migration_thread, NULL, migration_worker, - (void *)(unsigned long)syscall(SYS_gettid)); + spawn_threads(); for (i = 0; !done; i++) { vcpu_run(vcpu); @@ -258,7 +320,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2), "Only performed %d KVM_RUNs, task stalled too much?", i); - pthread_join(migration_thread, NULL); + join_threads(); kvm_vm_free(vm); -- 2.34.1

1 year, 7 months

3
4
0 0

[PATCH bpf-next v2 00/14] use start_server and connect_to helpers

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> v2: - update patch 6 only, fix errors reported by CI. This patchset uses public helpers start_server_* and connect_to_* defined in network_helpers.c to drop duplicate code. Geliang Tang (14): selftests/bpf: Add start_server_addr helper selftests/bpf: Use start_server_addr in cls_redirect selftests/bpf: Use connect_to_addr in cls_redirect selftests/bpf: Use start_server_addr in sk_assign selftests/bpf: Use connect_to_addr in sk_assign selftests/bpf: Use log_err in network_helpers selftests/bpf: Use start_server_addr in test_sock_addr selftests/bpf: Use connect_to_addr in test_sock_addr selftests/bpf: Add function pointer for __start_server selftests/bpf: Add start_server_setsockopt helper selftests/bpf: Use start_server_setsockopt in sockopt_inherit selftests/bpf: Use connect_to_fd in sockopt_inherit selftests/bpf: Use start_server_* in test_tcp_check_syncookie selftests/bpf: Use connect_to_addr in test_tcp_check_syncookie tools/testing/selftests/bpf/Makefile | 4 +- tools/testing/selftests/bpf/network_helpers.c | 50 ++++++++---- tools/testing/selftests/bpf/network_helpers.h | 4 + .../selftests/bpf/prog_tests/cls_redirect.c | 38 +--------- .../selftests/bpf/prog_tests/sk_assign.c | 53 +------------ .../bpf/prog_tests/sockopt_inherit.c | 64 ++++------------ tools/testing/selftests/bpf/test_sock_addr.c | 74 ++---------------- .../bpf/test_tcp_check_syncookie_user.c | 76 +++---------------- 8 files changed, 83 insertions(+), 280 deletions(-) -- 2.40.1

1 year, 7 months

3
20
0 0

[RFC PATCH v3 0/9] pids controller events rework and migration charging

by Michal Koutný

The series consists of two parts: - pids.events rework (originally v2, patches 1-6, - migration charging, patches 7-9. The changes are independent in principle, I stacked them for (my) convenience and because they both deserve RFC: 1) Changed semantics of v2 pids.events - similar change was proposed for memory.swap.events:max [1] 2) Migration charging is obsolete concept How are the new events supposed to be useful? - pids.events.local:max - tells that cgroup's limit is hit (too tight?) - pids.events.local:max.imposed - tells that cgroup's workload was restricted (generalization of 'cgroup: fork rejected by pids controller in %s' message) - pids.events:* - "only" directs top-down search to cgroups of interest The migration charging is motivated by apparenty surprising pids.current > pids.max because supervised processes are forked in supervisor's cgroup (more details in commit cgroup/pids: Enforce pids.max on task migrations too) Changes from v2 (https://lore.kernel.org/r/20200205134426.10570-1-mkoutny@suse.com) - implemented pids.events.local (Tejun) - added migration charging [1] https://lore.kernel.org/r/20230202155626.1829121-1-hannes@cmpxchg.org/ Michal Koutný (9): cgroup/pids: Remove superfluous zeroing cgroup/pids: Separate semantics of pids.events related to pids.max cgroup/pids: Make event counters hierarchical cgroup/pids: Add pids.events.local selftests: cgroup: Lexicographic order in Makefile selftests: cgroup: Add basic tests for pids controller cgroup/pids: Replace uncharge/charge pair with a single function cgroup/pids: Enforce pids.max on task migrations selftests: cgroup: Add tests pids controller Documentation/admin-guide/cgroup-v1/pids.rst | 3 +- Documentation/admin-guide/cgroup-v2.rst | 22 +- include/linux/cgroup-defs.h | 7 +- kernel/cgroup/cgroup.c | 16 +- kernel/cgroup/pids.c | 206 +++++++++---- tools/testing/selftests/cgroup/Makefile | 25 +- tools/testing/selftests/cgroup/test_pids.c | 302 +++++++++++++++++++ 7 files changed, 514 insertions(+), 67 deletions(-) create mode 100644 tools/testing/selftests/cgroup/test_pids.c base-commit: 026e680b0a08a62b1d948e5a8ca78700bfac0e6e -- 2.44.0

1 year, 7 months

5
20
0 0

[PATCH] kselftest: Mark functions that unconditionally call exit() as __noreturn

by Nathan Chancellor

After commit 6d029c25b71f ("selftests/timers/posix_timers: Reimplement check_timer_distribution()"), clang warns: tools/testing/selftests/timers/../kselftest.h:398:6: warning: variable 'major' is used uninitialized whenever '||' condition is true [-Wsometimes-uninitialized] 398 | if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2) | ^~~~~~~~~~~~ tools/testing/selftests/timers/../kselftest.h:401:9: note: uninitialized use occurs here 401 | return major > min_major || (major == min_major && minor >= min_minor); | ^~~~~ tools/testing/selftests/timers/../kselftest.h:398:6: note: remove the '||' if its condition is always false 398 | if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2) | ^~~~~~~~~~~~~~~ tools/testing/selftests/timers/../kselftest.h:395:20: note: initialize the variable 'major' to silence this warning 395 | unsigned int major, minor; | ^ | = 0 This is a false positive because if uname() fails, ksft_exit_fail_msg() will be called, which unconditionally calls exit(), a noreturn function. However, clang does not know that ksft_exit_fail_msg() will call exit() at the point in the pipeline that the warning is emitted because inlining has not occurred, so it assumes control flow will resume normally after ksft_exit_fail_msg() is called. Make it clear to clang that all of the functions that call exit() unconditionally in kselftest.h are noreturn transitively by marking them explicitly with '__attribute__((__noreturn__))', which clears up the warning above and any future warnings that may appear for the same reason. Fixes: 6d029c25b71f ("selftests/timers/posix_timers: Reimplement check_timer_distribution()") Reported-by: John Stultz <jstultz(a)google.com> Closes: https://lore.kernel.org/all/20240410232637.4135564-2-jstultz@google.com/ Signed-off-by: Nathan Chancellor <nathan(a)kernel.org> --- I have based this change on timers/urgent, as the commit that introduces this particular warning is there and it is marked for stable, even though this appears to be a generic kselftest issue. I think it makes the most sense for this change to go via timers/urgent with Shuah's ack. While __noreturn with a return type other than 'void' does not make much sense semantically, there are many places that these functions are used as the return value for other functions such as main(), so I did not change the return type of these functions from 'int' to 'void' to minimize the necessary changes for a backport (it is an existing issue anyways). I see there is another instance of this problem that will need to be addressed in -next, introduced by commit f07041728422 ("selftests: add ksft_exit_fail_perror()"). --- tools/testing/selftests/kselftest.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 973b18e156b2..0591974b57e0 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -80,6 +80,9 @@ #define KSFT_XPASS 3 #define KSFT_SKIP 4 +#ifndef __noreturn +#define __noreturn __attribute__((__noreturn__)) +#endif #define __printf(a, b) __attribute__((format(printf, a, b))) /* counters */ @@ -300,13 +303,13 @@ void ksft_test_result_code(int exit_code, const char *test_name, va_end(args); } -static inline int ksft_exit_pass(void) +static inline __noreturn int ksft_exit_pass(void) { ksft_print_cnts(); exit(KSFT_PASS); } -static inline int ksft_exit_fail(void) +static inline __noreturn int ksft_exit_fail(void) { ksft_print_cnts(); exit(KSFT_FAIL); @@ -333,7 +336,7 @@ static inline int ksft_exit_fail(void) ksft_cnt.ksft_xfail + \ ksft_cnt.ksft_xskip) -static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) +static inline __noreturn __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) { int saved_errno = errno; va_list args; @@ -348,19 +351,19 @@ static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) exit(KSFT_FAIL); } -static inline int ksft_exit_xfail(void) +static inline __noreturn int ksft_exit_xfail(void) { ksft_print_cnts(); exit(KSFT_XFAIL); } -static inline int ksft_exit_xpass(void) +static inline __noreturn int ksft_exit_xpass(void) { ksft_print_cnts(); exit(KSFT_XPASS); } -static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...) +static inline __noreturn __printf(1, 2) int ksft_exit_skip(const char *msg, ...) { int saved_errno = errno; va_list args; --- base-commit: 076361362122a6d8a4c45f172ced5576b2d4a50d change-id: 20240411-mark-kselftest-exit-funcs-noreturn-17d8ff729a7a Best regards, -- Nathan Chancellor <nathan(a)kernel.org>

1 year, 7 months

4
5
0 0

[PATCH net-next v6 0/6] net: gro: encapsulation bug fix and flush checks improvements

by Richard Gobert

This series fixes a bug in the complete phase of UDP in GRO, in which socket lookup fails due to using network_header when parsing encapsulated packets. The fix is to pass p_off parameter in *_gro_complete. Next, the fields network_offset and inner_network_offset are added to napi_gro_cb, and are both set during the receive phase of GRO. This is then leveraged in the next commit to remove flush_id state from napi_gro_cb, and stateful code in {ipv6,inet}_gro_receive which may be unnecessarily complicated due to encapsulation support in GRO. In addition, udpgro_fwd selftest is adjusted to include the socket lookup case for vxlan. This selftest will test its supposed functionality once local bind support is merged (https://lore.kernel.org/netdev/df300a49-7811-4126-a56a-a77100c8841b@gmail.c…). v5 -> v6: - Write inner_network_offset in vxlan, geneve and ipsec - Ignore is_atomic when DF=0 - v5: https://lore.kernel.org/all/20240408141720.98832-1-richardbgobert@gmail.com/ v4 -> v5: - Add 1st commit - flush id checks in udp_gro_receive segment which can be backported by itself - Add TCP measurements for the 5th commit - Add flush id tests to ensure flush id logic is preserved in GRO - Simplify gro_inet_flush by removing a branch - v4: https://lore.kernel.org/all/20240325182543.87683-1-richardbgobert@gmail.com/ v3 -> v4: - Fix code comment and commit message typos - v3: https://lore.kernel.org/all/f939c84a-2322-4393-a5b0-9b1e0be8ed8e@gmail.com/ v2 -> v3: - Use napi_gro_cb instead of skb->{offset} - v2: https://lore.kernel.org/all/2ce1600b-e733-448b-91ac-9d0ae2b866a4@gmail.com/ v1 -> v2: - Pass p_off in *_gro_complete to fix UDP bug - Remove more conditionals and memory fetches from inet_gro_flush - v1: https://lore.kernel.org/netdev/e1d22505-c5f8-4c02-a997-64248480338b@gmail.c… Richard Gobert (6): net: gro: add flush check in udp_gro_receive_segment net: gro: add p_off param in *_gro_complete selftests/net: add local address bind in vxlan selftest net: gro: add {inner_}network_offset to napi_gro_cb net: gro: move L3 flush checks to tcp_gro_receive and udp_gro_receive_segment selftests/net: add flush id selftests drivers/net/geneve.c | 8 +- drivers/net/vxlan/vxlan_core.c | 12 +- include/linux/etherdevice.h | 2 +- include/linux/netdevice.h | 3 +- include/linux/udp.h | 2 +- include/net/gro.h | 93 ++++++++++++-- include/net/inet_common.h | 2 +- include/net/tcp.h | 6 +- include/net/udp.h | 8 +- include/net/udp_tunnel.h | 2 +- net/8021q/vlan_core.c | 6 +- net/core/gro.c | 7 +- net/ethernet/eth.c | 5 +- net/ipv4/af_inet.c | 54 +------- net/ipv4/fou_core.c | 9 +- net/ipv4/gre_offload.c | 6 +- net/ipv4/tcp_offload.c | 22 +--- net/ipv4/udp.c | 3 +- net/ipv4/udp_offload.c | 31 +++-- net/ipv6/ip6_offload.c | 41 +++--- net/ipv6/tcpv6_offload.c | 7 +- net/ipv6/udp.c | 3 +- net/ipv6/udp_offload.c | 13 +- tools/testing/selftests/net/gro.c | 144 ++++++++++++++++++++++ tools/testing/selftests/net/udpgro_fwd.sh | 10 +- 25 files changed, 338 insertions(+), 161 deletions(-) -- 2.36.1

1 year, 7 months

2
14
0 0

[PATCH net-next 0/6] selftests: net: exercise page pool reporting via netlink

by Jakub Kicinski

Add a basic test for page pool netlink reporting. Jakub Kicinski (6): net: netdevsim: add some fake page pool use tools: ynl: don't return None for dumps selftests: net: print report check location in python tests selftests: net: print full exception on failure selftests: net: support use of NetdevSimDev under "with" in python selftests: net: exercise page pool reporting via netlink drivers/net/netdevsim/netdev.c | 93 ++++++++++++++++++++++ drivers/net/netdevsim/netdevsim.h | 4 + tools/net/ynl/lib/ynl.py | 4 +- tools/testing/selftests/net/lib/py/ksft.py | 29 ++++--- tools/testing/selftests/net/lib/py/nsim.py | 22 ++++- tools/testing/selftests/net/nl_netdev.py | 79 +++++++++++++++++- 6 files changed, 215 insertions(+), 16 deletions(-) -- 2.44.0

1 year, 7 months

3
12
0 0

[PATCH] selftests: timers: Fix valid-adjtimex signed left-shift undefined behavior

by John Stultz

So, the struct adjtimex freq field takes a signed value who's units are in shifted (<<16) parts-per-million. Unfortunately for negative adjustments, the straightforward use of: freq = ppm<<16 will trip undefined behavior warnings with clang: valid-adjtimex.c:66:6: warning: shifting a negative signed value is undefined [-Wshift-negative-value] -499<<16, ~~~~^ valid-adjtimex.c:67:6: warning: shifting a negative signed value is undefined [-Wshift-negative-value] -450<<16, ~~~~^ ... So fix our use of shifting negative values in the valid-adjtimex test case to use multiply by (1<<16) to avoid this. The patch also aligns the values a bit to make it look nicer. Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Stephen Boyd <sboyd(a)kernel.org> Cc: Anna-Maria Behnsen <anna-maria(a)linutronix.de> Cc: Frederic Weisbecker <frederic(a)kernel.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Nathan Chancellor <nathan(a)kernel.org> Cc: Nick Desaulniers <ndesaulniers(a)google.com> Cc: Lee Jones <joneslee(a)google.com> Cc: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Cc: linux-kselftest(a)vger.kernel.org Reported-by: Lee Jones <joneslee(a)google.com> Reported-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Link: https://lore.kernel.org/lkml/0c6d4f0d-2064-4444-986b-1d1ed782135f@collabora… Signed-off-by: John Stultz <jstultz(a)google.com> --- .../testing/selftests/timers/valid-adjtimex.c | 69 ++++++++++--------- 1 file changed, 35 insertions(+), 34 deletions(-) diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 48b9a803235a..9606d45767e7 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -62,45 +62,46 @@ int clear_time_state(void) #define NUM_FREQ_OUTOFRANGE 4 #define NUM_FREQ_INVALID 2 +#define SHIFTED_PPM (1 << 16) long valid_freq[NUM_FREQ_VALID] = { - -499<<16, - -450<<16, - -400<<16, - -350<<16, - -300<<16, - -250<<16, - -200<<16, - -150<<16, - -100<<16, - -75<<16, - -50<<16, - -25<<16, - -10<<16, - -5<<16, - -1<<16, + -499 * SHIFTED_PPM, + -450 * SHIFTED_PPM, + -400 * SHIFTED_PPM, + -350 * SHIFTED_PPM, + -300 * SHIFTED_PPM, + -250 * SHIFTED_PPM, + -200 * SHIFTED_PPM, + -150 * SHIFTED_PPM, + -100 * SHIFTED_PPM, + -75 * SHIFTED_PPM, + -50 * SHIFTED_PPM, + -25 * SHIFTED_PPM, + -10 * SHIFTED_PPM, + -5 * SHIFTED_PPM, + -1 * SHIFTED_PPM, -1000, - 1<<16, - 5<<16, - 10<<16, - 25<<16, - 50<<16, - 75<<16, - 100<<16, - 150<<16, - 200<<16, - 250<<16, - 300<<16, - 350<<16, - 400<<16, - 450<<16, - 499<<16, + 1 * SHIFTED_PPM, + 5 * SHIFTED_PPM, + 10 * SHIFTED_PPM, + 25 * SHIFTED_PPM, + 50 * SHIFTED_PPM, + 75 * SHIFTED_PPM, + 100 * SHIFTED_PPM, + 150 * SHIFTED_PPM, + 200 * SHIFTED_PPM, + 250 * SHIFTED_PPM, + 300 * SHIFTED_PPM, + 350 * SHIFTED_PPM, + 400 * SHIFTED_PPM, + 450 * SHIFTED_PPM, + 499 * SHIFTED_PPM, }; long outofrange_freq[NUM_FREQ_OUTOFRANGE] = { - -1000<<16, - -550<<16, - 550<<16, - 1000<<16, + -1000 * SHIFTED_PPM, + -550 * SHIFTED_PPM, + 550 * SHIFTED_PPM, + 1000 * SHIFTED_PPM, }; #define LONG_MAX (~0UL>>1) -- 2.44.0.478.gd926399ef9-goog

1 year, 7 months

4
3
0 0

[PATCH RFC bpf-next v6 0/6] sleepable bpf_timer (was: allow HID-BPF to do device IOs)

by Benjamin Tissoires

New version of the sleepable bpf_timer code. I'm posting this as this is the result of the previous review, so we can have a baseline to compare to. The plan is now to introduce a new user API struct bpf_wq, as the timer API working on softIRQ seems to be quite far away from a wq. For reference, the use cases I have in mind: --- Basically, I need to be able to defer a HID-BPF program for the following reasons (from the aforementioned patch): 1. defer an event: Sometimes we receive an out of proximity event, but the device can not be trusted enough, and we need to ensure that we won't receive another one in the following n milliseconds. So we need to wait those n milliseconds, and eventually re-inject that event in the stack. 2. inject new events in reaction to one given event: We might want to transform one given event into several. This is the case for macro keys where a single key press is supposed to send a sequence of key presses. But this could also be used to patch a faulty behavior, if a device forgets to send a release event. 3. communicate with the device in reaction to one event: We might want to communicate back to the device after a given event. For example a device might send us an event saying that it came back from sleeping state and needs to be re-initialized. Currently we can achieve that by keeping a userspace program around, raise a bpf event, and let that userspace program inject the events and commands. However, we are just keeping that program alive as a daemon for just scheduling commands. There is no logic in it, so it doesn't really justify an actual userspace wakeup. So a kernel workqueue seems simpler to handle. bpf_timers are currently running in a soft IRQ context, this patch series implements a sleppable context for them. Cheers, Benjamin To: Alexei Starovoitov <ast(a)kernel.org> To: Daniel Borkmann <daniel(a)iogearbox.net> To: Andrii Nakryiko <andrii(a)kernel.org> To: Martin KaFai Lau <martin.lau(a)linux.dev> To: Eduard Zingerman <eddyz87(a)gmail.com> To: Song Liu <song(a)kernel.org> To: Yonghong Song <yonghong.song(a)linux.dev> To: John Fastabend <john.fastabend(a)gmail.com> To: KP Singh <kpsingh(a)kernel.org> To: Stanislav Fomichev <sdf(a)google.com> To: Hao Luo <haoluo(a)google.com> To: Jiri Olsa <jolsa(a)kernel.org> To: Mykola Lysenko <mykolal(a)fb.com> To: Shuah Khan <shuah(a)kernel.org> Cc: Benjamin Tissoires <bentiss(a)kernel.org> Cc: <bpf(a)vger.kernel.org> Cc: <linux-kernel(a)vger.kernel.org> Cc: <linux-kselftest(a)vger.kernel.org> --- Changes in v6: - Use of a workqueue to clean up sleepable timers - integrated Kumar's patch instead of mine - Link to v5: https://lore.kernel.org/r/20240322-hid-bpf-sleepable-v5-0-179c7b59eaaa@kern… Changes in v5: - took various reviews into account - rewrote the tests to be separated to not have a uggly include - Link to v4: https://lore.kernel.org/r/20240315-hid-bpf-sleepable-v4-0-5658f2540564@kern… Changes in v4: - dropped the HID changes, they can go independently from bpf-core - addressed Alexei's and Eduard's remarks - added selftests - Link to v3: https://lore.kernel.org/r/20240221-hid-bpf-sleepable-v3-0-1fb378ca6301@kern… Changes in v3: - fixed the crash from v2 - changed the API to have only BPF_F_TIMER_SLEEPABLE for bpf_timer_start() - split the new kfuncs/verifier patch into several sub-patches, for easier reviews - Link to v2: https://lore.kernel.org/r/20240214-hid-bpf-sleepable-v2-0-5756b054724d@kern… Changes in v2: - make use of bpf_timer (and dropped the custom HID handling) - implemented bpf_timer_set_sleepable_cb as a kfunc - still not implemented global subprogs - no sleepable bpf_timer selftests yet - Link to v1: https://lore.kernel.org/r/20240209-hid-bpf-sleepable-v1-0-4cc895b5adbd@kern… --- Benjamin Tissoires (5): bpf/helpers: introduce sleepable bpf_timers bpf/helpers: introduce bpf_timer_set_sleepable_cb() kfunc bpf/helpers: mark the callback of bpf_timer_set_sleepable_cb() as sleepable tools: sync include/uapi/linux/bpf.h selftests/bpf: add sleepable timer tests Kumar Kartikeya Dwivedi (1): bpf: Add support for KF_ARG_PTR_TO_TIMER include/linux/bpf_verifier.h | 1 + include/uapi/linux/bpf.h | 13 ++ kernel/bpf/helpers.c | 202 ++++++++++++++++--- kernel/bpf/verifier.c | 98 +++++++++- tools/include/uapi/linux/bpf.h | 20 +- tools/testing/selftests/bpf/bpf_experimental.h | 5 + .../selftests/bpf/bpf_testmod/bpf_testmod.c | 5 + .../selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h | 1 + tools/testing/selftests/bpf/prog_tests/timer.c | 34 ++++ .../testing/selftests/bpf/progs/timer_sleepable.c | 213 +++++++++++++++++++++ 10 files changed, 553 insertions(+), 39 deletions(-) --- base-commit: 61df575632d6b39213f47810c441bddbd87c3606 change-id: 20240205-hid-bpf-sleepable-c01260fd91c4 Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

1 year, 7 months

5
20
0 0

[PATCH v3 00/30] NT synchronization primitive driver

by Elizabeth Figura

This patch series introduces a new char misc driver, /dev/ntsync, which is used to implement Windows NT synchronization primitives. == Background == The Wine project emulates the Windows API in user space. One particular part of that API, namely the NT synchronization primitives, have historically been implemented via RPC to a dedicated "kernel" process. However, more recent applications use these APIs more strenuously, and the overhead of RPC has become a bottleneck. The NT synchronization APIs are too complex to implement on top of existing primitives without sacrificing correctness. Certain operations, such as NtPulseEvent() or the "wait-for-all" mode of NtWaitForMultipleObjects(), require direct control over the underlying wait queue, and implementing a wait queue sufficiently robust for Wine in user space is not possible. This proposed driver, therefore, implements the problematic interfaces directly in the Linux kernel. This driver was presented at Linux Plumbers Conference 2023. For those further interested in the history of synchronization in Wine and past attempts to solve this problem in user space, a recording of the presentation can be viewed here: https://www.youtube.com/watch?v=NjU4nyWyhU8 == Performance == The gain in performance varies wildly depending on the application in question and the user's hardware. For some games NT synchronization is not a bottleneck and no change can be observed, but for others frame rate improvements of 50 to 150 percent are not atypical. The following table lists frame rate measurements from a variety of games on a variety of hardware, taken by users Dmitry Skvortsov, FuzzyQuils, OnMars, and myself: Game Upstream ntsync improvement =========================================================================== Anger Foot 69 99 43% Call of Juarez 99.8 224.1 125% Dirt 3 110.6 860.7 678% Forza Horizon 5 108 160 48% Lara Croft: Temple of Osiris 141 326 131% Metro 2033 164.4 199.2 21% Resident Evil 2 26 77 196% The Crew 26 51 96% Tiny Tina's Wonderlands 130 360 177% Total War Saga: Troy 109 146 34% =========================================================================== == Patches == The intended semantics of the patches are broadly intended to match those of the corresponding Windows functions. For those not already familiar with the Windows functions (or their undocumented behaviour), patch 31/31 provides a detailed specification, and individual patches also include a brief description of the API they are implementing. The patches making use of this driver in Wine can be retrieved or browsed here: https://repo.or.cz/wine/zf.git/shortlog/refs/heads/ntsync5 == Implementation == Some aspects of the implementation may deserve particular comment: * In the interest of performance, each object is governed only by a single spinlock. However, NTSYNC_IOC_WAIT_ALL requires that the state of multiple objects be changed as a single atomic operation. In order to achieve this, we first take a device-wide lock ("wait_all_lock") any time we are going to lock more than one object at a time. The maximum number of objects that can be used in a vectored wait, and therefore the maximum that can be locked simultaneously, is 64. This number is NT's own limit. The acquisition of multiple spinlocks will degrade performance. This is a conscious choice, however. Wait-for-all is known to be a very rare operation in practice, especially with counts that approach the maximum, and it is the intent of the ntsync driver to optimize wait-for-any at the expense of wait-for-all as much as possible. * NT mutexes are tied to their threads on an OS level, and the kernel includes builtin support for "robust" mutexes. In order to keep the ntsync driver self-contained and avoid touching more code than necessary, it does not hook into task exit nor use pids. Instead, the user space emulator is expected to manage thread IDs and pass them as an argument to any relevant functions; this is the "owner" field of ntsync_wait_args and ntsync_mutex_args. When the emulator detects that a thread dies, it should therefore call NTSYNC_IOC_MUTEX_KILL on any open mutexes. * ntsync is module-capable mostly because there was nothing preventing it, and because it aided development. It is not a hard requirement, though. == Previous versions == Changes from v2: * Check the result of fget() for NULL. * Squash patch 31 (introducing the NTSYNC_WAIT_REALTIME flag) into patch 4, per Arnd Bergmann. * Use atomic_try_cmpxchg() instead of atomic_cmpxchg(), per off-list review from Uros Bizjak. * Link to v2: https://lore.kernel.org/lkml/20240219223833.95710-1-zfigura@codeweavers.com/ * Link to v1: https://lore.kernel.org/lkml/20240214233645.9273-1-zfigura@codeweavers.com/ * Link to RFC v2: https://lore.kernel.org/lkml/20240131021356.10322-1-zfigura@codeweavers.com/ * Link to RFC v1: https://lore.kernel.org/lkml/20240124004028.16826-1-zfigura@codeweavers.com/ Elizabeth Figura (30): ntsync: Introduce the ntsync driver and character device. ntsync: Introduce NTSYNC_IOC_CREATE_SEM. ntsync: Introduce NTSYNC_IOC_SEM_POST. ntsync: Introduce NTSYNC_IOC_WAIT_ANY. ntsync: Introduce NTSYNC_IOC_WAIT_ALL. ntsync: Introduce NTSYNC_IOC_CREATE_MUTEX. ntsync: Introduce NTSYNC_IOC_MUTEX_UNLOCK. ntsync: Introduce NTSYNC_IOC_MUTEX_KILL. ntsync: Introduce NTSYNC_IOC_CREATE_EVENT. ntsync: Introduce NTSYNC_IOC_EVENT_SET. ntsync: Introduce NTSYNC_IOC_EVENT_RESET. ntsync: Introduce NTSYNC_IOC_EVENT_PULSE. ntsync: Introduce NTSYNC_IOC_SEM_READ. ntsync: Introduce NTSYNC_IOC_MUTEX_READ. ntsync: Introduce NTSYNC_IOC_EVENT_READ. ntsync: Introduce alertable waits. selftests: ntsync: Add some tests for semaphore state. selftests: ntsync: Add some tests for mutex state. selftests: ntsync: Add some tests for NTSYNC_IOC_WAIT_ANY. selftests: ntsync: Add some tests for NTSYNC_IOC_WAIT_ALL. selftests: ntsync: Add some tests for wakeup signaling with WINESYNC_IOC_WAIT_ANY. selftests: ntsync: Add some tests for wakeup signaling with WINESYNC_IOC_WAIT_ALL. selftests: ntsync: Add some tests for manual-reset event state. selftests: ntsync: Add some tests for auto-reset event state. selftests: ntsync: Add some tests for wakeup signaling with events. selftests: ntsync: Add tests for alertable waits. selftests: ntsync: Add some tests for wakeup signaling via alerts. selftests: ntsync: Add a stress test for contended waits. maintainers: Add an entry for ntsync. docs: ntsync: Add documentation for the ntsync uAPI. Documentation/userspace-api/index.rst | 1 + .../userspace-api/ioctl/ioctl-number.rst | 2 + Documentation/userspace-api/ntsync.rst | 399 +++++ MAINTAINERS | 9 + drivers/misc/Kconfig | 11 + drivers/misc/Makefile | 1 + drivers/misc/ntsync.c | 1166 ++++++++++++++ include/uapi/linux/ntsync.h | 62 + tools/testing/selftests/Makefile | 1 + .../testing/selftests/drivers/ntsync/Makefile | 8 + tools/testing/selftests/drivers/ntsync/config | 1 + .../testing/selftests/drivers/ntsync/ntsync.c | 1407 +++++++++++++++++ 12 files changed, 3068 insertions(+) create mode 100644 Documentation/userspace-api/ntsync.rst create mode 100644 drivers/misc/ntsync.c create mode 100644 include/uapi/linux/ntsync.h create mode 100644 tools/testing/selftests/drivers/ntsync/Makefile create mode 100644 tools/testing/selftests/drivers/ntsync/config create mode 100644 tools/testing/selftests/drivers/ntsync/ntsync.c base-commit: 4cece764965020c22cff7665b18a012006359095 -- 2.43.0

1 year, 7 months

4
36
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror